Health Care Professionals (HCPs) depend on self-directed learning by watching medical videos. In the traditional video learning system, it is difficult to identify the important videos from the huge data set and to find the essential inside parts of a long video. In addition, it is hard to know learners’ preferences inside the video parts, including duration and repetition of watching. If the system could know the attention and retention process of each learner, it could change the way to show the video. Accordingly, this research proposes to design the Video Aided Retention Tool (VART) system for analyzing video content to improve self-directed video-based learning among HCPs. The VART consists of a combination of video tracking, analyzing, and filtering tools, with the integration of domain model, learners’ model, and e-teaching strategy model to aid in self-directed learning. The proposed VART will pick important videos on a single topic and put automatic indexes to represent the essential parts of video content. It will also track the learner’s ID, content preference, monitor watching duration, and repetition of the content. Using such kind of data, attention, and retention will be determined and filtered reels, recommendations, interactive videos will be provided to the learners.

中文翻译：

---

自我导向的基于视频的学习中的保健专业人员的视频辅助工具的设计

卫生保健专业人员（HCP）通过观看医学视频来依靠自主学习。在传统的视频学习系统中，很难从庞大的数据集中识别出重要的视频，也很难找到长视频的重要内部部分。此外，很难在视频部分内了解学习者的喜好，包括持续时间和重复观看。如果系统可以了解每个学习者的注意力和保留过程，则可以改变显示视频的方式。因此，本研究提出设计视频辅助保留工具（VART）系统来分析视频内容，以改善HCP之间基于自我指导的视频学习。VART包含视频跟踪，分析和过滤工具的组合，以及域模型，学习者模型，和电子教学策略模型来辅助自主学习。拟议的VART将在单个主题上挑选重要的视频，并放置自动索引以表示视频内容的基本部分。它还将跟踪学习者的ID，内容偏好，监控观看时间以及内容的重复。使用此类数据，可以确定注意力和留存率，并过滤卷轴，推荐内容和交互式视频，并将其提供给学习者。